MLC LLM
llm.mlc.ai
A universal LLM deployment engine that compiles models to run natively on laptops, phones, and browsers — the same model, the same weights, running on NVIDIA, AMD, Apple Silicon, or WebGPU.
Why it is useful
The only framework that genuinely targets every hardware target from a single model compilation step. Running a quantized Llama model natively on an iPhone or an Android device without a server is something most frameworks cannot do. The browser deployment via WebGPU is the technology powering WebLLM. Useful for anyone building AI applications that need to run at the edge without cloud dependencies.
More in Hidden Websites
Other hidden websites you might not have heard of.
- Library of Short StoriesFree collection of classic short stories from various authors in a simple reading format.
- Heavens-AbovePredicts when satellites, including the International Space Station, will pass over your location, with sky charts and visibility times.
- Atomic RocketsA huge reference on realistic spaceship design, space travel physics and settings for science fiction writers and game designers, part of Project Rho.
- FeedbinA clean, fast RSS reader that also lets you subscribe to email newsletters and read them in the same feed as your other subscriptions.
- theindex.fyiA maintained index of the indie web and small web directories, search engines and aggregators, with a note on which ones are still active.
- WikisourceA free library of source texts, including books, documents and historical papers, transcribed and proofread by volunteers.